Difference between revisions of "3D Form and Motion"

From RedwoodCenter
Jump to navigationJump to search
 
(2 intermediate revisions by the same user not shown)
Line 25: Line 25:
  
 
'''Kinect'''
 
'''Kinect'''
* KinectFusion
+
* KinectFusion [http://www.youtube.com/watch?v=quGhaggn3cQ&sns=em demo]
 
** UIST 2011 paper [http://redwood.berkeley.edu/bruno/3DFM/kinect-fusion.pdf pdf]
 
** UIST 2011 paper [http://redwood.berkeley.edu/bruno/3DFM/kinect-fusion.pdf pdf]
 
** IEEE conf paper [http://redwood.berkeley.edu/bruno/3DFM/kinect-fusion-IEEE.pdf pdf]
 
** IEEE conf paper [http://redwood.berkeley.edu/bruno/3DFM/kinect-fusion-IEEE.pdf pdf]
Line 38: Line 38:
 
* Thrun, "Probabilistic algorithms in robotics" [http://redwood.berkeley.edu/bruno/3DFM/thrun-SLAM.pdf pdf]
 
* Thrun, "Probabilistic algorithms in robotics" [http://redwood.berkeley.edu/bruno/3DFM/thrun-SLAM.pdf pdf]
 
* Daniel Cremers work on helicopters/SLAM (TU Munich) [http://vision.in.tum.de/research URL]
 
* Daniel Cremers work on helicopters/SLAM (TU Munich) [http://vision.in.tum.de/research URL]
 +
* Davison references on monocular SLAM [http://www.doc.ic.ac.uk/%7Eajd/publications.html URL]
 
* Newcombe and Davison, "Live dense reconstruction with a single moving camera work on fast single camera", [http://redwood.berkeley.edu/bruno/3DFM/newcombe-davison.pdf pdf]
 
* Newcombe and Davison, "Live dense reconstruction with a single moving camera work on fast single camera", [http://redwood.berkeley.edu/bruno/3DFM/newcombe-davison.pdf pdf]
  
Line 52: Line 53:
 
* Polani et al. "From unknown sensors and actuators to actions" [http://redwood.berkeley.edu/bruno/3DFM/polani-robot.pdf pdf]
 
* Polani et al. "From unknown sensors and actuators to actions" [http://redwood.berkeley.edu/bruno/3DFM/polani-robot.pdf pdf]
 
* Robotics paper trying to perceive environment based on sensiromotor loop (from Pulkit): [http://www.aaai.org/Papers/AAAI/2007/AAAI07-174.pdf pdf]
 
* Robotics paper trying to perceive environment based on sensiromotor loop (from Pulkit): [http://www.aaai.org/Papers/AAAI/2007/AAAI07-174.pdf pdf]
 +
 +
'''Eye movements:'''
 +
* Glennerster et al. (2001) "Fixation could simplify, not complicate, the interpretation of retinal flow" [http://redwood.berkeley.edu/bruno/3DFM/glennerster-fixation.pdf pdf]
 +
* Daniilidis, K. (1997)  "Fixation simplifies 3D motion estimation."  Computer Vision and Image Understanding, 68(2), 158--169.
  
 
'''Manifolds:'''
 
'''Manifolds:'''
 
* Manifolds in computer vision tutorial: [http://redwood.berkeley.edu/bruno/3DFM/manifolds.pdf pdf]
 
* Manifolds in computer vision tutorial: [http://redwood.berkeley.edu/bruno/3DFM/manifolds.pdf pdf]
 
** references: [http://www.cs.fsu.edu/~liux/manifold-short-course/reference.html URL]
 
** references: [http://www.cs.fsu.edu/~liux/manifold-short-course/reference.html URL]

Latest revision as of 23:06, 15 September 2013

Mondays at 1:00, Evans 560

3D models from images:

  • Hartley and Zisserman: Multiple View Geometry (Amazon)
  • Hoiem and Savarese: 3D object recognition and scene interpretation, book pdf
  • Hoiem Ph.D. thesis "SEEING THE WORLD BEHIND THE IMAGE" pdf
  • Cashman and Fitzgibbon: "What Shape are Dolphins? Building 3D Morphable Models from 2D Images" pdf
  • Snavely and Seitz (2006), "Photo tourism" (aka photosynth), pdf
  • Seitz google talk on history of 3D computer vision: URL
    • Blanz and Vetter, 3D face models pdf
    • Tomasi and Kanade, factorization of shape and motion, pdf
  • Blanz & Vetter (2003) "Face Recognition Based on Fitting a 3D Morphable Model" pdf
  • Atick & Redlich papers:
    • "The vocabulary of shape: principal shapes for probing perception and neural response" pdf
    • "Statistical Approach to Shape from Shading: Reconstruction of Three-Dimensional Face Surfaces from Single Two-Dimensional Images" pdf
  • Bregler, Hertzmann, "Recovering non-rigid 3D shape from image streams" pdf
  • Allen, Curless, Popovic, "The space of human body shapes: reconstruction and parameterization from range scans" pdf
  • Suggested by Pulkit:
    • D Ramanan, "Analyzing 3D Objects in Cluttered Images" pdf
    • B Schiele, first couple of papers at url
  • Gal et al., "Local shape priors" pdf
  • Jon Barron's papers url
  • Pentland, "A Possible Neural Mechanism for Computing Shape From Shading" pdf

Kinect

  • KinectFusion demo
    • UIST 2011 paper pdf
    • IEEE conf paper pdf

3D data sets

  • Princeton Shape data set: url
  • Ponce: url
  • Silberman url

SLAM:

  • wiki page with list of refs
  • Thrun, "Probabilistic algorithms in robotics" pdf
  • Daniel Cremers work on helicopters/SLAM (TU Munich) URL
  • Davison references on monocular SLAM URL
  • Newcombe and Davison, "Live dense reconstruction with a single moving camera work on fast single camera", pdf

Psychophysics:

  • Nakayama et al. (1995) "Visual Surface Representation" pdf
  • Glennerster and Fitzgibbon, "View-Based Approaches to Spatial Representation in Human Vision" pdf
  • Wexler work on depth from self-motion/parallax, reference frames, pdf1, pdf2

Action-perception:

  • Philipona et al. Neural Computation (2003) pdf
    • Follow on papers URL
  • Philipona et al. NIPS (2003) pdf
    • Follow on papers URL
  • Polani et al. "From unknown sensors and actuators to actions" pdf
  • Robotics paper trying to perceive environment based on sensiromotor loop (from Pulkit): pdf

Eye movements:

  • Glennerster et al. (2001) "Fixation could simplify, not complicate, the interpretation of retinal flow" pdf
  • Daniilidis, K. (1997) "Fixation simplifies 3D motion estimation." Computer Vision and Image Understanding, 68(2), 158--169.

Manifolds:

  • Manifolds in computer vision tutorial: pdf
    • references: URL